EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

abCRISPR: deep learning-based design of abasic gRNA sequences for specific CRISPR-Cas9 genome editing

Geun-Woo D Kim, Dowoon Gu, Mingyo Park, Sung Wook Chi iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag568 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Geun-Woo D Kim und 3 weiteren Autor:innen. Beteiligte Einrichtung: KU-KIST Graduate School of Converging Science and Technology, Korea University, Seoul 02841, Korea. Hauptthemen laut MEDLINE: Deep Learning, CRISPR-Cas Systems, RNA, Guide, CRISPR-Cas Systems, Gene Editing. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Ministry of Science and ICT and Ministry of Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Summary CRISPR-Cas9 has become a widely used tool for genome editing. However, its off-target cleavage caused by partial sequence matches with guide RNAs (gRNAs) remains a critical limitation. Recently, abasic gRNAs (ØXØ) have been developed to enhance target specificity, but their effects vary depending on the positional sequence context. Here, we present abCRISPR, a deep neural network (DNN) framework for the rational design of ØXØ sequences with minimized off-target activity. abCRISPR leverages informative few-shot training with paired datasets of abasic and unmodified gRNAs, using high-quality random mismatch target libraries, exhaustively sequenced for mismatched off-target substrates (n = 97583) in in vitro CRISPR-Cas9 cleavage experiments. Predicted off-target activities for both abasic and unmodified gRNAs showed strong correlation with experimental data (r ≥ 0.95, 10-fold cross-validation). Notably, these comprehensive training sets provide robust ground-truth negatives, enabling accurate and sensitive prediction of off-targets. For unmodified gRNAs, abCRISPR (AUC = 0.98) was validated to outperform existing deep learning-based methods (AUC = 0.45–0.68). When applied to the human genome, abCRISPR generated ØXØ sequences, covering 58 875 004 potent CRISPR-targetable sites with improved target specificity. Together, this work provides a comprehensive bioinformatics resource for safe and precise CRISPR-Cas9 genome editing. Availability and implementation The source code for abCRISPR and training data are available at https://doi.org/10.5281/zenodo.20398246. abCRISPR results for the human genome are available at http://clip.korea.ac.kr/abCRISPR/

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCRISPR-Cas SystemsRNA, Guide, CRISPR-Cas SystemsGene EditingSoftwareHumansBase Sequence

Substanzen

RNA, Guide, CRISPR-Cas Systems

Autor:innen und Institutionen

  • KU-KIST Graduate School of Converging Science and Technology, Korea University, Seoul 02841, Korea.
  • Department of Life Sciences, Korea University, Seoul 02841, Korea.
  • National Research Laboratory for Convergence Degradation Biology, Korea University, Seoul 02841, Korea.
  • Medicinal Materials Research Center, Biomedical Research Division, Korea Institute of Science and Technology (KIST), Seoul 02841, Korea.

ORCID-Profile: Sung Wook Chi

Förderung

  • National Research Foundation of Korea
  • Ministry of Science and ICT and Ministry of Education

Zitieren

APA

Kim, G. D., Gu, D., Park, M., & Chi, S. W. (2026). abCRISPR: deep learning-based design of abasic gRNA sequences for specific CRISPR-Cas9 genome editing. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag568

Vancouver

Kim GD, Gu D, Park M, Chi SW. abCRISPR: deep learning-based design of abasic gRNA sequences for specific CRISPR-Cas9 genome editing. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag568

BibTeX
@article{Kim2026,
  author = {Kim, Geun-Woo D and Gu, Dowoon and Park, Mingyo and Chi, Sung Wook},
  title = {abCRISPR: deep learning-based design of abasic gRNA sequences for specific CRISPR-Cas9 genome editing},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag568}
}
Kostenlos starten →